Abstract. In recent years, there has been a great deal of work in modeling audio using non-negative matrix factorization and its probabilistic counterparts as they yield rich model...
In this paper, we tackle the problem of understanding the temporal structure of complex events in highly varying videos obtained from the Internet. Towards this goal, we utilize a...
In this paper, a video segmentation algorithm based on Hidden Markov Model classifier with multimodal feature is proposed. By using Hidden Markov Model classifier with both audio a...
This paper proposes a novel method to detect flames in video by processing the data generated by an ordinary camera monitoring a scene. In addition to ordinary motion and color cl...
We propose a video event analysis framework based on object segmentation and tracking, combined with a Hidden Semi-Markov Model (HSMM) that uses state occupancy duration modeling....